A Laravel web application integrated with Ollama for AI-powered Q&A functionality. This application allows users to ask questions and receive intelligent responses generated by local language models.

• 🤖 AI Chat Interface - Ask questions and get responses from local language models
• 🔗 RESTful API - Clean API endpoints for AI interactions
• ⚡ Laravel Framework - Built with Laravel for robust web development
• 🏠 Local AI - Uses Ollama for running language models locally
• 📝 Request Validation - Proper input validation and error handling

Before running this application, make sure you have the following installed:

• PHP >= 8.1
• Composer - PHP dependency manager
• Laravel - Web framework
• Ollama - Local LLM service (for AI functionality)
• Node.js & npm (optional, for frontend assets)

1. Clone the repository:

   git clone <repository-url>
   cd edu-ai

2. Install PHP dependencies:

   composer install

3. Install Node.js dependencies (optional):

   npm install

4. Set up environment:

   cp .env.example .env
   php artisan key:generate

5. Install and start Ollama:

   # Install Ollama (Linux)
   curl -fsSL https://ollama.ai/install.sh | sh
   
   # Pull a language model
   ollama pull phi3:mini
   
   # Start Ollama service
   sudo systemctl start ollama
   sudo systemctl enable ollama

6. Start the Laravel development server:

   php artisan serve

The application provides a RESTful API for AI interactions:

Ask a question and receive an AI-generated response.

Request:

{
  "question": "What is machine learning?"
}

Response:

{
  "question": "What is machine learning?",
  "answer": "Machine learning is a subset of artificial intelligence that enables computers to learn and improve from experience without being explicitly programmed...",
  "model": "phi3:mini"
}

You can test the API using curl:

curl -X POST http://localhost:8000/api/ask-ai \
  -H "Content-Type: application/json" \
  -d '{"question": "What is crypto?"}'

The application is configured to connect to Ollama running on localhost:11434. Make sure:

1. Ollama service is running: sudo systemctl status ollama
2. At least one model is available: ollama list
3. The model specified in AIController.php exists

The application currently uses phi3:mini by default. You can change this in app/Http/Controllers/AIController.php:

'model' => 'phi3:mini', // Change to 'llama3' or other models

├── app/
│   ├── Http/Controllers/
│   │   └── AIController.php    # Main AI interaction logic
│   └── Models/                 # Eloquent models
├── routes/
│   └── api.php                 # API route definitions
├── public/                     # Public web assets
└── storage/                    # Application storage

1. "Unable to connect to Ollama"

   • Ensure Ollama service is running: sudo systemctl start ollama
   • Check if port 11434 is accessible: curl http://localhost:11434/api/tags

2. Slow responses

   • The application uses a 180-second timeout for AI requests
   • Consider using smaller models like phi3:mini for better performance
   • Monitor system resources (CPU/Memory usage)

3. Model not found

   • Pull the required model: ollama pull phi3:mini
   • List available models: ollama list

• Laravel logs: storage/logs/laravel.log
• Ollama logs: journalctl -u ollama --no-pager

php artisan test

npm run build
# or for development
npm run dev

This project is licensed under the MIT License.

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if necessary
5. Submit a pull request

Built with ❤️ using Laravel and Ollama